Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add nagisanzenin/idiolect/plugin install idiolectWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nagisanzenin/idiolect/humanize)<a href="https://agentmods.dev/skills/nagisanzenin/idiolect/humanize"><img src="https://agentmods.dev/badge/skills/nagisanzenin/idiolect/humanize.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.00862 |
| Opus 5 | $0.00030 | $0.00431 |
| Sonnet 5 | $0.00012 | $0.00172 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
humanize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/idiolect:humanize — from slop to person
Two modes. Both end with before/after scanner scores, because "sounds better to me" is not a receipt.
Voice references can be fuzzy and human ("make it sound like the diner guy", "like me" → the self voice): resolve against $IDIO voices --json and proceed, mentioning the match in passing. No voice mentioned → Mode A.
Setup
ROOT="${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-$IDIOLECT_ROOT}}"
# unset everywhere (opencode)? ROOT = two directories up from this SKILL.md
IDIO="python3 $ROOT/scripts/idiolect.py"
Input text goes to a scratch file via the Write tool, never inline in shell.
Mode A — scrub and soul (no voice given)
The goal is the same author, minus the generator fingerprints, plus a pulse.
- Save input to
orig.txt; run$IDIO scan --file orig.txt [--platform <p>]. Show the user the score and the top tells found — this is the "before" receipt and it teaches them what was wrong. - Rewrite with three obligations:
- Kill every flagged tell (the report gives line numbers): the lexical slop, the constructions ("It's not X. It's Y."), the metronomic sentence lengths, the wrap-up ending, the bold-header bullets.
- Preserve every factual claim exactly. Scrubbing is not summarizing; if the original has five specifics, the rewrite has five specifics. NEVER add facts that aren't in the original — if it's thin on specifics, tell the user that's the real problem (specificity is the strongest human signal there is) and ask for two or three true details worth adding.
- Restore a pulse: vary sentence lengths (target CV ≥ 0.55), let one opinion or ambivalence through, cut the throat-clearing, end without a bow. Register stays the author's own — formal text stays formal; don't inflict aggressive casualness (that's the "humanizer house style," and it's the next tell).
- Re-scan the rewrite. Target ≤ 15 (≤ 20 for formal registers). Iterate to 3 times.
- Deliver: rewrite in a fenced block +
receipt: 68 → 9 (clean)+ one line on the biggest change.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 49 lines · 60 tokens per session scan A 4c4fed45b6a1
humanize is a skill published in the GitHub repository nagisanzenin/idiolect (23 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 862 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…